quantization-aware-training
There are 59 repositories under quantization-aware-training topic.
brandontang892/quant_aware_L2Grad_regularization
Our work implements novel L2-Norm gradient (L2Grad) and variance of the weight distrbution (VarianceNorm) regularizers for quantization-aware training such that the distribution of weights are more compatible with post-training quantization especially for low bit-widths. We provide a theoretical basis that directly relates L2-Grad with post quantization test accuracy through a first order Taylor Series expansion followed by the reduction to an adversary with an L2 budget, in which we apply the Cauchy-Schwarz inequality to provide the desired bounds. We empirically show that L2Grad and VarianceNorm can both match the performance of L1Grad and outperform it on certain bit-widths. We also show that a regularization scheme that combines L2Grad and VarianceNorm in a novel "regularization scheduling" methodology can give even better results in terms of post-quantization accuracy, tested on uniform and piecewise linear quantization.
d-becking/ECQx
ECQx: Explainability-Driven Quantization for Low-Bit and Sparse DNNs
iabd/QuantizedNMT
8 bit quantizated Transformer for neural machine translation.
jahongir7174/PIPNet-qat
Quantization Aware Training
OmidGhadami95/EfficientNetV2_Quantization_CK
EfficientNetV2 (Efficientnetv2-b2) and quantization int8 and fp32 (QAT and PTQ) on CK+ dataset . fine-tuning, augmentation, solving imbalanced dataset, etc.
stracini-git/qnn
Training neural nets with quantized weights on arbitrarily specified bit-depth
SuperbTUM/Transformer-Quantization
Transformer quantization and binarization exploration
TanyaChutani/Quantization_Tensorflow
Quantization for Object Detection in Tensorflow 2.x
anhtunguyen98/NMT-Huggingface
NMT training pipeline using huggingface transformer
BGUCompSci/CNNQuantizationThroughPDEs
Code repository for the paper Quantized Convolutional Neural Networks Through the Lens of Partial Differential Equations
HanByulKim/vis-quant
Visualizing DNN Quantization effect on Network.
lixilinx/Flexible_quantization
A simple formula supports eight types of quantization
rishivar/adversarial-notebooks
Experimental Adversarial Attack notebooks on CV models
zoetu/DynamicQuantization_Bert
DynamicQuantization_Bert from pytorch tutorials
alexeybelkov/MedQ
Implementation of MedQ: Lossless ultra-low-bit neural network quantization for medical image segmentation
ambideXtrous9/Quantization-of-Models-PTQ-and-QAT
Quantization of Models : Post-Training Quantization(PTQ) and Quantize Aware Training(QAT)
DaraVaram/Quant
Quantization notebooks (adapted from and for Mobile Apps w/ Machine Learning, By Dara Varam and Lujain Khalil)
insuofficial/pytorch-quantization
Quantization simulation of neural networks with PyTorch
maryamsoftdev/Quantization-in-Machine-Learning
A Tutorial Notebook to Quantization in Machine Learning
project-sulsul/SulSul-AI
Classify alcohols and its snacks
sjlee94/AI
CNN quantization